{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:F4EMRQLD67VTW3EGLVIFPLNBXY","short_pith_number":"pith:F4EMRQLD","schema_version":"1.0","canonical_sha256":"2f08c8c163f7eb3b6c865d5057ada1be0391c87ccb3ecf6a088ac1b7f08efe85","source":{"kind":"arxiv","id":"2605.26672","version":1},"attestation_state":"computed","paper":{"title":"Can We Hear from Events? Generating Speech from Event Camera","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"cs.MM","authors_text":"Chenyang Xu, Jingping Fang, Lin Chen, Tong Zhao, Weidong Cai, Xiaoming Chen","submitted_at":"2026-05-26T08:11:27Z","abstract_excerpt":"Traditional RGB-based speech generation faces Temporal Granularity Mismatch since fixed camera exposure times inevitably blur the high-frequency articulatory transients essential for rendering emotional speech. To break this ceiling, we propose EventSpeech as a novel text-conditioned framework pioneering the use of neuromorphic events for expressive speech generation, since these microsecond-precise events naturally align with acoustic waveform dynamics. Our architecture integrates a dedicated Event Encoder to model sparse neuromorphic events alongside a multi-scale Audio Encoder featuring a H"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2605.26672","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2026-05-26T08:11:27Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"712cb4fb4804cfe469ac1ea483f4dd0a456316919f367abd83a0c0cf5eab2667","abstract_canon_sha256":"0aec304c89829ccba145a5f6ebc7ad7f1f786633265a9be83a4e5fcc4e1193a5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-27T01:06:05.240384Z","signature_b64":"YXbuvs6Ln6FFpUdz/Jaabm7yGxReI7a1AH/txmr7VQ0sszgcUKInb8qDnGOuI1Nqc5GYs4t3JjXs0m0yF1KIBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2f08c8c163f7eb3b6c865d5057ada1be0391c87ccb3ecf6a088ac1b7f08efe85","last_reissued_at":"2026-05-27T01:06:05.239610Z","signature_status":"signed_v1","first_computed_at":"2026-05-27T01:06:05.239610Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Can We Hear from Events? Generating Speech from Event Camera","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"cs.MM","authors_text":"Chenyang Xu, Jingping Fang, Lin Chen, Tong Zhao, Weidong Cai, Xiaoming Chen","submitted_at":"2026-05-26T08:11:27Z","abstract_excerpt":"Traditional RGB-based speech generation faces Temporal Granularity Mismatch since fixed camera exposure times inevitably blur the high-frequency articulatory transients essential for rendering emotional speech. To break this ceiling, we propose EventSpeech as a novel text-conditioned framework pioneering the use of neuromorphic events for expressive speech generation, since these microsecond-precise events naturally align with acoustic waveform dynamics. Our architecture integrates a dedicated Event Encoder to model sparse neuromorphic events alongside a multi-scale Audio Encoder featuring a H"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.26672","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.26672/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2605.26672","created_at":"2026-05-27T01:06:05.239716+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.26672v1","created_at":"2026-05-27T01:06:05.239716+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.26672","created_at":"2026-05-27T01:06:05.239716+00:00"},{"alias_kind":"pith_short_12","alias_value":"F4EMRQLD67VT","created_at":"2026-05-27T01:06:05.239716+00:00"},{"alias_kind":"pith_short_16","alias_value":"F4EMRQLD67VTW3EG","created_at":"2026-05-27T01:06:05.239716+00:00"},{"alias_kind":"pith_short_8","alias_value":"F4EMRQLD","created_at":"2026-05-27T01:06:05.239716+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/F4EMRQLD67VTW3EGLVIFPLNBXY","json":"https://pith.science/pith/F4EMRQLD67VTW3EGLVIFPLNBXY.json","graph_json":"https://pith.science/api/pith-number/F4EMRQLD67VTW3EGLVIFPLNBXY/graph.json","events_json":"https://pith.science/api/pith-number/F4EMRQLD67VTW3EGLVIFPLNBXY/events.json","paper":"https://pith.science/paper/F4EMRQLD"},"agent_actions":{"view_html":"https://pith.science/pith/F4EMRQLD67VTW3EGLVIFPLNBXY","download_json":"https://pith.science/pith/F4EMRQLD67VTW3EGLVIFPLNBXY.json","view_paper":"https://pith.science/paper/F4EMRQLD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.26672&json=true","fetch_graph":"https://pith.science/api/pith-number/F4EMRQLD67VTW3EGLVIFPLNBXY/graph.json","fetch_events":"https://pith.science/api/pith-number/F4EMRQLD67VTW3EGLVIFPLNBXY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F4EMRQLD67VTW3EGLVIFPLNBXY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F4EMRQLD67VTW3EGLVIFPLNBXY/action/storage_attestation","attest_author":"https://pith.science/pith/F4EMRQLD67VTW3EGLVIFPLNBXY/action/author_attestation","sign_citation":"https://pith.science/pith/F4EMRQLD67VTW3EGLVIFPLNBXY/action/citation_signature","submit_replication":"https://pith.science/pith/F4EMRQLD67VTW3EGLVIFPLNBXY/action/replication_record"}},"created_at":"2026-05-27T01:06:05.239716+00:00","updated_at":"2026-05-27T01:06:05.239716+00:00"}